Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jpicklyk/task-orchestrator/api-compat-reviewnpx skills add jpicklyk/task-orchestrator --skill api-compat-reviewgit clone --depth 1 https://github.com/jpicklyk/task-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jpicklyk/task-orchestrator/api-compat-review)<a href="https://agentmods.dev/skills/jpicklyk/task-orchestrator/api-compat-review"><img src="https://agentmods.dev/badge/skills/jpicklyk/task-orchestrator/api-compat-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.00554 |
| Opus 5 | $0.00024 | $0.00277 |
| Sonnet 5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
api-compat-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Compatibility Review Framework
Assess API changes by surface — the MCP tool surface (dynamically re-discovered by clients) and the REST surface (hardcoded clients) have different compatibility models. Do not apply REST-style breaking-change caution to MCP tools, and do not apply MCP's rename-friendliness to REST.
Step 1: Classify the Change
Determine which surface(s) the change touches:
- MCP tools —
application/tools/tool definitions,parameterSchema, tooldescriptionstrings - REST API —
interfaces/api/v1/routes/,interfaces/api/v1/dto/Dtos.kt,openapi.yaml
A single change (e.g., a domain model field rename) can touch both surfaces independently — assess each.
Step 2: MCP Surface Assessment
LLM clients re-read the tools/list schema every session — there is no persistent client binding to break. A pure parameter rename does NOT require keeping the old name working. Verify instead:
- Every changed param's
parameterSchemakey and its arg-parsing read site stay in sync — no schema-says-X/code-reads-Y drift - ALL first-party callers update in lockstep: plugin skills, hooks, output styles, auto-memory references, and
api-reference.md. This doc coordination is the real cost of an MCP change, not client breakage. - The tool
descriptionstring accurately reflects the new behavior
Step 3: REST Surface Assessment
HTTP clients hardcode field and param names, so compatibility DOES matter here:
- Response-shape changes are additive (new fields only) where possible
- Renames or removals of existing fields/params have an explicit migration path or version bump — not a silent break
- Note when a surface has effectively zero consumers (e.g., a days-old endpoint) so the reviewer can right-size caution instead of over-indexing on hypothetical clients
-
openapi.yamlis updated for any REST-facing change -
api-rest.mdis updated for any REST-facing change
Output
Compose the api-compatibility note with findings from Step 2 and/or Step 3, scoped to whichever surface(s) the change actually touches. If a surface wasn't touched, say so explicitly rather than omitting it silently.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 38 lines · 49 tokens per session scan A 5f594ea5bac6
api-compat-review is a skill published in the GitHub repository jpicklyk/task-orchestrator (206 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 554 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pneuma-project
Project-context awareness — multi-session workflows around one topic, shared materials and preferences, and cross-mode handoffs as a high-value user path.
vc-generate-phase-program
Generate kickoff artifacts for a multi-phase program: umbrella plan, Program Goal Charter, session-goal block, per-phase plan stubs, and the 7-step per-phase inner loop reference.
vc-intent-clarify
Clarify intent before RIPER-5 phase delegation. Scores ambiguity (4 signals); generates structured multi-choice questions for Tier 2. Two-mode: SIMPLE and DEEP.
vc-agent-browser
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
vc-scenario
Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions. Use before implementation or testing to catch issues early.
vc-audit-context
Audit project context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.